LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to instruct LLMs proficiently poses a challenge for non-AI experts. Existing research in prompt engineering suggests somewhat scattered optimization principles and designs empirically dependent prompt optimizers. Unfortunately, these endeavors lack a structured design template, incurring high learning costs and resulting in low reusability. In addition, it is not conducive to the iterative updating of prompts. Inspired by structured reusable programming languages, we propose LangGPT, a dual-layer prompt design framework as the programming language for LLMs. LangGPT has an easy-to-learn normative structure and provides an extended structure for migration and reuse. Experiments illustrate that LangGPT significantly enhances the performance of LLMs. Moreover, the case study shows that LangGPT leads LLMs to generate higher-quality responses. Furthermore, we analyzed the ease of use and reusability of LangGPT through a user survey in our online community.
@article{arxiv.2402.16929,
title = {LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language},
author = {Ming Wang and Yuanzhong Liu and Xiaoyu Liang and Songlian Li and Yijie Huang and Xiaoming Zhang and Sijia Shen and Chaofeng Guan and Daling Wang and Shi Feng and Huaiwen Zhang and Yifei Zhang and Minghui Zheng and Chi Zhang},
journal= {arXiv preprint arXiv:2402.16929},
year = {2024}
}